Skip to main content

Claude Opus 5.5 (Adaptive Reasoning, High Effort, Default Fallback)

AnthropicClaude
Release Date
2026-09-22
Parameters
—
Context Length
1.0M
Modalities
image, pdf, text

Capability Radar

54
general
60
coding
32
reasoning
59
science
40
agents
80
multimodal

Rankings

Domain#RankScoreSource
Code Ranking32
93.0
AA
General Ranking4
93.0
AA
Science10
90.0
AA

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

No benchmark data available

AA Evaluation Indices

(Artificial Analysis)
Lcr(Artificial Analysis)
82.7
Scicode(UIUC + Argonne National Lab (2024))
60.4
Hle(Center for AI Safety + Scale AI (2025))
55.6
Intelligence Index(Artificial Analysis)
53.6

LLM Stats Category Scores

(LLM Stats (zeroeval))

No category score data available

Pricing

Input Price$4 / 1M tokens
Output Price$20 / 1M tokens
Blended Price (3:1)$8 / 1M tokens
Cache Read Price$0.2 / 1M tokens
Cache Write Price$5 / 1M tokens

Speed

Tokens/sec76.1
Time to First Token16.92s
Time to Answer16.92s

Provider Price Ranking

Provider Price Ranking

1 providers

ProviderInputOutput
1AnthropicPRIMARY
$4
$20

Compare pricing across different API providers for this model.

External Sources